Scholarlink

In this chapter, we study semi-supervised edge learning, where the model is first initialized via resource-efficient FL across many edge devices and then personalized for an edge device with limited data samples. In particular, we delve into adaptive device selection and scheduling problem for improving the performance and efficiency of FL by taking the device heterogeneity and resource constraints into consideration.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Resource-Efficient Edge AI via Personalized Federated Learning

  • 章节

  • 发表日期：

    2025年

查看全文
  • Sen Lin,
  • Zhi Zhou,
  • Zhaofeng Zhang,
  • Xu Chen,
  • Junshan Zhang

摘要

In this chapter, we study semi-supervised edge learning, where the model is first initialized via resource-efficient FL across many edge devices and then personalized for an edge device with limited data samples. In particular, we delve into adaptive device selection and scheduling problem for improving the performance and efficiency of FL by taking the device heterogeneity and resource constraints into consideration.